© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 14919
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their roles or accomplishments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Precedes verbs like "earned", "holds", or "was"

    np_acts-logits-general · gemini-2.0-flash

    holds, earned, or is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnchorStyles
    -0.70
    __((
    -0.54
     Apparently
    -0.54
    Shouldn
    -0.54
     zaten
    -0.53
    mybatisplus
    -0.53
    ControllerAdvice
    -0.52
    abestanden
    -0.51
    Kanpo
    -0.51
    Apparently
    -0.51
    POSITIVE LOGITS
     earned
    0.88
     received
    0.80
     graduated
    0.79
     holds
    0.75
     completed
    0.68
    earned
    0.65
     erwar
    0.64
     nakalista
    0.63
     gained
    0.62
     hold
    0.62
    Activations Density 0.153%

    No Known Activations